Methods and systems for identifying and projecting recurrent event patterns in information technology infrastructure

1. A method for identifying and projecting recurrent event patterns in an Information Technology (IT) infrastructure, the method comprising: deriving, by a network device, at least one time period based on historical events data of the IT infrastructure, wherein deriving the at least one time period comprises identifying at least one frequent event interval upon identifying discontinuity periods in the historical events data; grouping, by the network device, the historical events data comprising a plurality of events captured for the IT infrastructure, based on the at least one time period to create a plurality of data points sets, wherein each data points set is associated with one of the at least one time period and comprises at least one event from the plurality of events; creating, by the network device, an event corpus comprising each of the plurality of events arranged based on frequency of occurrence across the plurality of data points sets; identifying, by the network device, one or more events that have highest frequency of occurrence within the event corpus, wherein the identifying is iteratively performed on the event corpus, each subsequent iteration of the identifying ignores events identified in preceding iterations of the identifying; determining, by the network device, one or more data points sets from the plurality of data points sets in which the one or more events have occurred; and computing, by the network device, a projected frequency of occurrence of the one or more events in future time periods corresponding to the one or more data points sets based on variation in frequency of occurrence of the one or more events in the one or more data points sets.

2. The method of claim 1 further comprising: retrieving the historical events data associated with the IT infrastructure; and storing the historical events data in a predefined representation.

3. The method of claim 1 , wherein deriving a time period of the at least one time period comprises: segregating events in the historical events data based on a time of occurrence across a plurality of one-hour intervals; and adding zero in at least one of the plurality of one hour intervals having non-occurrence of an event.

4. The method of claim 3 further comprising identifying discontinuity periods within the plurality of one-hour intervals based on occurrence of zeros.

5. The method of claim 4 further comprising identifying most frequently occurring discontinuity period amongst the discontinuity periods.

6. The method of claim 1 , wherein events in a data points set from the plurality of data points sets are arranged based on frequency of occurrence of each event in the data points set.

7. The method of claim 1 , wherein determining the one or more data points sets comprises identifying a set of events from the one or more events that occur in same data points sets from the plurality of data points sets, the one or more data points sets are determined for the set of events.

8. The method of claim 1 , wherein computing the projected frequency of occurrence of an event from the one or more events comprises determining variation in frequency of occurrence of the event across the one or more data points sets.

9. The method of claim 8 further comprising, comparing the total number of positive frequency variations and the total number of negative frequency variations for the event across the one or more data points sets.

10. The method of claim 9 further comprising increasing frequency of occurrence of the event in each subsequent time period within the future time periods by an average of the total positive frequency variations to compute a projected frequency of occurrence for the event in each subsequent time period, when the number of total positive frequency variations is greater than the number of total negative frequency variations.

11. The method of claim 9 further comprising decreasing frequency of occurrence of the event in each subsequent time period within the future time periods by an average of the total negative frequency variations to compute a projected frequency of occurrence for the event in each subsequent time period, when the number of total negative frequency variations is greater than the number of total positive frequency variations.

12. A network device for identifying and projecting recurrent event patterns in an Information Technology (IT) infrastructure, the network device comprising: at least one processor; and a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to: derive at least one time period based on historical events data of the IT infrastructure, wherein to derive the at least one time period, the processor instructions, on execution, further causes the processor to identify at least one frequent event interval upon identifying discontinuity periods in the historical events data; group the historical events data comprising a plurality of events captured for the IT infrastructure, based on the at least one time period to create a plurality of data points sets, wherein each data points set is associated with one of the at least one time period and comprises at least one event from the plurality of events; create an event corpus comprising each of the plurality of events arranged based on frequency of occurrence across the plurality of data points sets; identify one or more events that have highest frequency of occurrence within the event corpus, wherein the processor instructions, on execution, further causes the processor to identify the one or more events within the event corpus iteratively, wherein each subsequent iteration of the identifying ignores events identified in preceding iterations of the identifying; determine one or more data points sets from the plurality of data points sets in which the one or more events have occurred; and compute a projected frequency of occurrence of the one or more events in future time periods corresponding to the one or more data points sets based on variation in frequency of occurrence of the one or more events in the one or more data points sets.

13. The network device of claim 12 , wherein the processor instructions, on execution, further causes the processor to: retrieve the historical events data associated with the IT infrastructure; and store the historical events data in a predefined representation.

14. The network device of claim 12 , wherein to derive a time period of the at least one time period, the processor instructions, on execution, further causes the processor to: segregating events in the historical events data based on a time of occurrence across a plurality of one-hour intervals; and adding zero in at least one of the plurality of one hour intervals having non-occurrence of an event.

15. The network device of claim 14 , wherein the processor instructions, on execution, further causes the processor to identify discontinuity periods within the plurality of one-hour intervals based on occurrence of zeros.

16. The network device of claim 15 , wherein the processor instructions, on execution, further causes the processor to identify most frequently occurring discontinuity period amongst the discontinuity periods.

17. The network device of claim 12 , wherein to compute the projected frequency of occurrence of an event from the one or more events, the processor instructions, on execution, further causes the processor to determine variation in frequency of occurrence of the event across the one or more data points sets.

18. The network device of claim 17 , wherein the processor instructions, on execution, further causes the processor to compare the total number of positive frequency variations and the total number of negative frequency variations for the event across the one or more data points sets.

19. A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions for identifying and projecting recurrent event patterns in an Information Technology (IT) infrastructure, causing a computer comprising one or more processors to perform steps comprising: deriving, by a network device, at least one time period based on historical events data of the IT infrastructure, wherein deriving the at least one time period comprises identifying at least one frequent event interval upon identifying discontinuity periods in the historical events data; grouping, by the network device, the historical events data comprising a plurality of events captured for the IT infrastructure, based on the at least one time period to create a plurality of data points sets, wherein each data points set is associated with one of the plurality of time periods and comprises at least one event from the plurality of events; creating, by the network device, an event corpus comprising each of the plurality of events arranged based on frequency of occurrence across the plurality of data points sets; identifying, by the network device, one or more events that have highest frequency of occurrence within the event corpus, wherein the identifying is iteratively performed on the event corpus, each subsequent iteration of the identifying ignores events identified in preceding iterations of the identifying; determining, by the network device, one or more data points sets from the plurality of data points sets in which the one or more events have occurred; and computing, by the network device, a projected frequency of occurrence of the one or more events in future time periods corresponding to the one or more data points sets based on variation in frequency of occurrence of the one or more events in the one or more data points sets.